NVIDIA GeForce GTX 660 Ti vs AMD Radeon HD 6870

VS
Performance
GeForce GTX 660 Ti100% better
8,4158% of 104,598
Radeon HD 6870
4,2184% of 104,598

The GeForce GTX 660 Ti has 100% better performance than the Radeon HD 6870 for the 3DMark 11 Performance GPU benchmark.

Performance per dollar
GeForce GTX 660 Ti59% better
28.1417% of 161.45
Radeon HD 6870
17.6511% of 161.45

The GeForce GTX 660 Ti has 59% better value for the money than the Radeon HD 6870 for the 3DMark 11 Performance GPU benchmark.

Shop GeForce GTX 660 Ti
Shop Radeon HD 6870
As an Amazon Associate I earn from qualifying purchases.

Summary

#

About the NVIDIA GeForce GTX 660 Ti GPU

The NVIDIA GeForce GTX 660 Ti is an end-of-life desktop graphics card that released in Q3 2012 with a MSRP of $299. It is built on the Kepler GPU microarchitecture (codename GK104) and is manufactured on a 28 nm process.

Memory

The GTX 660 Ti has 2 GB of GDDR5 memory, with a 1,502 MHz memory clock and a 192 bit interface. This gives it a memory bandwidth of 144.2 Gb/s, which affects how fast it can transfer data to and from memory. GPU memory stores temporary data that helps the GPU with complex math and graphics operations. More memory is generally better, as not having enough can cause performance bottlenecks.

Cores and Clock Speeds

The GTX 660 Ti includes 1,344 CUDA cores, the processing units for handling parallel computing tasks. The GPU operates at a core clock speed of 915 MHz and can dynamically boost its clock speed up to 980 MHz. Complementing the processing units are 112 texture mapping units (TMUs) for efficient texture filtering and 24 render output units (ROPs) for pixel processing.

Compatibility & Power Consumption

The GTX 660 Ti occupies 2 PCIe expansion slots. It supports DVI, HDMI 1.4a, DisplayPort 1.2 display connections. NVIDIA recommends a power supply of at least 450 W to handle the GPU's thermal design power (TDP) of 150 W.

Benchmark Performance & Value

The GTX 660 Ti has the 197th best 3DMark 11 Performance GPU score among the 543 benchmarked GPUs in our database. It achieves 8.05% of the performance of the best benchmarked GPU, the NVIDIA GeForce RTX 4090. Its 8,415 score and $299 launch price (MSRP) gives it a performance per dollar of 28.14. This is the 81st best in value for the 3DMark 11 Performance GPU benchmark.

About the AMD Radeon HD 6870 GPU

The AMD Radeon HD 6870 is an end-of-life desktop graphics card that released in Q4 2010 with a MSRP of $239. It is built on the TeraScale 2 GPU microarchitecture (codename Barts) and is manufactured on a 40 nm process.

Memory

The HD 6870 has 1,024 MB of GDDR5 memory, with a 1,050 MHz memory clock and a 256 bit interface. This gives it a memory bandwidth of 134.4 Gb/s, which affects how fast it can transfer data to and from memory. GPU memory stores temporary data that helps the GPU with complex math and graphics operations. More memory is generally better, as not having enough can cause performance bottlenecks.

Cores and Clock Speeds

The HD 6870 includes 1,120 stream processors (SPs), the processing units for handling parallel computing tasks. The GPU operates at a core clock speed of 900 MHz. Complementing the processing units are 56 texture mapping units (TMUs) for efficient texture filtering and 32 render output units (ROPs) for pixel processing.

Compatibility & Power Consumption

The HD 6870 occupies 2 PCIe expansion slots. It supports DVI, HDMI 1.3a, mini-DisplayPort 1.1 display connections. AMD recommends a power supply of at least 450 W to handle the GPU's thermal design power (TDP) of 151 W.

Benchmark Performance & Value

The HD 6870 has the 269th best 3DMark 11 Performance GPU score among the 543 benchmarked GPUs in our database. It achieves 4.03% of the performance of the best benchmarked GPU, the NVIDIA GeForce RTX 4090. Its 4,218 score and $239 launch price (MSRP) gives it a performance per dollar of 17.65. This is the 91st best in value for the 3DMark 11 Performance GPU benchmark.

General Info

General overview of the GPU, including details like its manufacturer, release date, launch price, and current production status.

InfoGeForce GTX 660 TiRadeon HD 6870
ManufacturerNVIDIAAMD
ArchitectureKeplerTeraScale 2
Market SegmentDesktopDesktop
Release DateQ3 2012Q4 2010
Launch Price (MSRP)$299$239
Production StatusEnd-of-lifeEnd-of-life
ShopCheck PriceCheck Price

Gaming Performance

#

Select a game to compare FPS metrics

Display FPS for BioShock Infinite
BioShock Infinite
Display FPS for Counter-Strike: Global Offensive
CS: GO

FPS Benchmarks

This table showcases the average frame rate (FPS) achieved both GPUs in at various resolutions. Frame rate is a crucial indicator of how smoothly the GPU can run the game. A higher FPS generally translates to a smoother gameplay experience.

  • Frames Per Second
FPS data for BioShock Infinite
BioShock Infinite
GeForce GTX 660 TiRadeon HD 6870
Low - 720p
201 FPS
--
Medium - 768p
169 FPS
--
High - 768p
151 FPS
--
Ultra - 1080p
63 FPS
--
QHD - 1440p
--
--
4K UHD - 2160p
--
--
FPS Source: Notebookcheck

Compare Frames Per Second (FPS)

The average frame rate (FPS) in can be compared to similar GPUs to assess relative performance. Generally, higher FPS results in a smoother gameplay experience.

Choose Baseline GPU:GeForce GTX 660 Ti orRadeon HD 6870

Compare Cost Per Frame

The average cost per frame in can be compared to similar GPUs to assess relative value. Generally, a lower cost per frame implies better value for your money.

Choose Baseline GPU:GeForce GTX 660 Ti orRadeon HD 6870

Benchmark Performance

#
Performance
GeForce GTX 660 Ti100% better
8,4158% of 104,598
Radeon HD 6870
4,2184% of 104,598

The GeForce GTX 660 Ti has 100% better performance than the Radeon HD 6870 for the 3DMark 11 Performance GPU benchmark.

The GeForce GTX 660 Ti is ranked 197th with a score of 8,415, and the Radeon HD 6870 is ranked 269th with a score of 4,218.

Performance per dollar
GeForce GTX 660 Ti59% better
28.1417% of 161.45
Radeon HD 6870
17.6511% of 161.45

The GeForce GTX 660 Ti has 59% better value for the money than the Radeon HD 6870 for the 3DMark 11 Performance GPU benchmark.

The GeForce GTX 660 Ti is ranked 81st with a performance per dollar of 28.14, and the Radeon HD 6870 is ranked 91st with a performance per dollar of 17.65.

Relative Performance

The average score in the benchmark test can be compared to similar GPUs to assess relative performance. Generally, powerful GPUs tend to have higher scores.

Choose Baseline GPU:GeForce GTX 660 Ti or

Relative Value For Money

The average performance per dollar in the benchmark test can be compared to similar GPUs to assess relative value. A higher score implies a better value for your money.

Choose Baseline GPU:GeForce GTX 660 Ti or

Benchmark Scores

This table showcases the average performance scores achieved by both GPUs across industry-standard benchmark tests. These scores provide a valuable insight into overall performance. Powerful GPUs tend to have higher scores.

  • Popular
BenchmarkGeForce GTX 660 TiRadeon HD 6870
3DMark Cloud Gate Graphics
37,758
(+42.82%)
26,437
3DMark Fire Strike Standard Graphics
5,432
(+72.94%)
3,141
3DMark 11 Performance Score
7,693
(+69.17%)
4,547.5
PassMark G3D Mark
4,429
(+99.86%)
2,216
PassMark G2D Mark
467
(+13.35%)
412
Unigine Heaven 3.0 DirectX 11
78.7
--
Benchmarks Source: Notebookcheck

Technical Specs

#

Graphics Processor

General information about the graphics processing unit like their architecture, manufacturing process size, and transistor count. Newer GPU architectures generally bring efficiency improvements and may introduce technologies that enhance graphical capabilities.

SpecGeForce GTX 660 TiRadeon HD 6870
CodenameGK104Barts
ArchitectureKeplerTeraScale 2
Process Size28 nm40 nm
Transistors3,540 million1,700 million

Memory Details

Memory specifications like their capacity, bandwidth, and clock speeds. GPU memory stores graphics data like frames, textures, and shadows which helps display rendered images. These specs are crucial for graphics-intense applications like gaming and 3D modeling.

SpecGeForce GTX 660 TiRadeon HD 6870
Memory Size2 GB1,024 MB
Memory TypeGDDR5GDDR5
Memory Bandwidth144.2 Gb/s134.4 Gb/s
Memory Clock1,502 MHz1,050 MHz
Memory Interface192 bit256 bit
L1 Cache16 KB8 KB
L2 Cache384 KB512 KB

Board Compatibility

Compatibility information like their slot size, bus interface, power consumption, and display support. These specs are useful for verifying compatibility with your motherboard, power supply, and monitor.

SpecGeForce GTX 660 TiRadeon HD 6870
Slots2 slots2 slots
Bus InterfacePCIe 3.0 x16PCIe 2.0 x16
Thermal Design Power (TDP)150 W151 W
Suggested PSU450 W450 W
Power Connectors2x 6-pin2x 6-pin
OutputsDVI, HDMI 1.4a, DisplayPort 1.2DVI, HDMI 1.3a, mini-DisplayPort 1.1

Cores & Clock Speeds

Processing power information like its cores and clock speed. These specs impact how fast they can process graphics. Each type of core or component serves a specific computational purpose.

SpecGeForce GTX 660 TiRadeon HD 6870
Stream Processors (SP)--1,120
CUDA Cores1,344--
Compute Units (CU)--14
Stream Multiprocessors (SM)7--
Texture Mapping Units (TMU)11256
Render Output Units (ROP)2432
Core Clock Speed915 MHz900 MHz
Core Clock Speed (Boost)980 MHz--

Theoretical Performance

Theoretical performance numbers derived from the raw specifications of the different components like core count and clock speeds. While these provide a glimpse into peak processing power, they do not represent real-world performance.

SpecGeForce GTX 660 TiRadeon HD 6870
Pixel Fill Rate27.44 GPixel/s28.8 GPixel/s
Texture Fill Rate109.8 GTexel/s50.4 GTexel/s
FP32 Performance2.63 TFLOPS2.02 TFLOPS
FP64 Performance109.8 GFLOPS--

API Support

Graphics API versions supported by these graphics cards. APIs evolve over time, introducing new features and functionalities. Older GPUs may not support recent versions.

SpecGeForce GTX 660 TiRadeon HD 6870
DirectX12 (11_0)11.2 (11_0)
OpenCL3.01.2
OpenGL4.64.4
Shader Model6.5 (5.1)5.0

Check out these comparisons for similar GPUs:

Looking for alternatives? Check out these similar GPUs:

* Performance rating, performance per dollar, and rankings are based on the 3DMark 11 Performance GPU benchmark and MSRP.